Machine learning analysis method, system and equipment based on visual dragging and medium

Abstract

The invention discloses a machine learning analysis method, system and device based on visual dragging and a medium, and the method comprises the steps: responding to a dragging operation of a user on a function node icon, and displaying a machine learning flow chart on a front-end page; in response to a first operation of a user on the function node icon, updating the node configuration information; the node configuration information comprises at least one of a data source, a parameter and a model operator type of the machine learning model; and transmitting the machine learning flow chart to a background for processing, calling a model operator corresponding to the machine learning flow chart to build a machine learning model, and training and storing the machine learning model. According to the method, a mainstream machine learning algorithm can be modularized to obtain a plurality of machine learning model operators, and a user is assisted to efficiently complete complex business modeling, so that the application threshold and cost of a machine learning model are reduced. The method can be widely applied to the technical field of artificial intelligence.

Description

technical field [0001] This application relates to the technical field of artificial intelligence, especially a machine learning analysis method, system, device and medium based on visual dragging. Background technique [0002] In recent years, with the development of artificial intelligence technology, the technology of machine learning has received extensive attention. Machine learning is a multi-field interdisciplinary subject, involving probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and other disciplines, specializing in the study of how computers simulate or implement human learning behaviors to acquire new knowledge or Skills, reorganize the existing knowledge structure to continuously improve its own performance. [0003] Among related technologies, traditional machine learning requires a lot of manpower to study in depth, covering probability theory knowledge, statistical knowledge, approximate theoretical knowledg...

AI Technical Summary

Problems solved by technology

[0003] Among related technologies, traditional machine learning requires a lot of manpower to study in depth, covering probability theory knowledge, statistical knowledge, approximate theoretical knowledge, and complex algorithm knowledge. The threshold for use is relatively high, limited by the limitations of these machine learning algorithms. And shortcomings, it is difficult to promote the application of machine learning on a large scale, there is a lot of repetitive work in related machine learning applications, and the development efficiency is low

Images